ML ISTART: Difference between revisions

From VASP Wiki
No edit summary
No edit summary
Line 6: Line 6:
*{{TAG|ML_FF_ISTART}}=0: The training calculations are started from scratch without taking any existing data into considerations. Learning is executed.
*{{TAG|ML_FF_ISTART}}=0: The training calculations are started from scratch without taking any existing data into considerations. Learning is executed.
*{{TAG|ML_FF_ISTART}}=1: The program reads the training data stored in the {{TAG|ML_AB}} file and restarts the training calculation. Learning is executed.
*{{TAG|ML_FF_ISTART}}=1: The program reads the training data stored in the {{TAG|ML_AB}} file and restarts the training calculation. Learning is executed.
*{{TAG|ML_FF_ISTART}}=2: The program reads the training data stored in the {{TAG|ML_AB}} file and force field parameters stored in the {{TAG|ML_FF}} file and executes calculations using the force field only. No learning is executed.
*{{TAG|ML_FF_ISTART}}=2: The program reads the force field parameters stored in the {{TAG|ML_FF}} file and executes calculations using the force field only. No learning is executed.


== Related Tags and Sections ==
== Related Tags and Sections ==

Revision as of 08:08, 9 June 2021

ML_FF_ISTART = [integer]
Default: ML_FF_ISTART = 0 

Description: This tag decides if and how calculations are continued from existing data in machine learning force field method.


The following cases can be selected:

  • ML_FF_ISTART=0: The training calculations are started from scratch without taking any existing data into considerations. Learning is executed.
  • ML_FF_ISTART=1: The program reads the training data stored in the ML_AB file and restarts the training calculation. Learning is executed.
  • ML_FF_ISTART=2: The program reads the force field parameters stored in the ML_FF file and executes calculations using the force field only. No learning is executed.

Related Tags and Sections

ML_FF_LMLFF, ML_FF_W1_MB, ML_FF_WTOTEN, ML_FF_WTIFOR, ML_FF_WTSIF

Examples that use this tag